{"id":"https://openalex.org/W2788374150","doi":"https://doi.org/10.1109/icassp.2018.8462523","title":"Improved Tdnns Using Deep Kernels and Frequency Dependent Grid-RNNS","display_name":"Improved Tdnns Using Deep Kernels and Frequency Dependent Grid-RNNS","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2788374150","doi":"https://doi.org/10.1109/icassp.2018.8462523","mag":"2788374150"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1802.06412","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069221660","display_name":"Florian Kreyssig","orcid":"https://orcid.org/0000-0002-8948-988X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"F. L. Kreyssig","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K","Cambridge University Engineering Department, Trumpington St., Cambridge CB2 1PZ, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Cambridge University Engineering Department, Trumpington St., Cambridge CB2 1PZ, U.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460139","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-1018-4144"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"C. Zhang","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K","Cambridge University Engineering Department, Trumpington St., Cambridge CB2 1PZ, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Cambridge University Engineering Department, Trumpington St., Cambridge CB2 1PZ, U.K","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. C. Woodland","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K","Cambridge University Engineering Department, Trumpington St., Cambridge CB2 1PZ, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Cambridge University Engineering Department, Trumpington St., Cambridge CB2 1PZ, U.K","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069221660"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.39712492,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65368227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4864","last_page":"4868"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8112715482711792},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7876052856445312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6114583015441895},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.599726676940918},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5964421033859253},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5623593330383301},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5623522996902466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5001838207244873},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.44933176040649414},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4202398657798767},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41987210512161255},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4089089035987854},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40035688877105713},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2800709307193756},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0914364755153656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8112715482711792},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7876052856445312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6114583015441895},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.599726676940918},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5964421033859253},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5623593330383301},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5623522996902466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001838207244873},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.44933176040649414},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4202398657798767},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41987210512161255},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4089089035987854},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40035688877105713},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2800709307193756},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0914364755153656},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2018.8462523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1802.06412","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06412","pdf_url":"https://arxiv.org/pdf/1802.06412","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2788374150","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1802.06412","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:generic.eprints.org:1033759","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/1033759/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"doi:10.48550/arxiv.1802.06412","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.06412","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1802.06412","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06412","pdf_url":"https://arxiv.org/pdf/1802.06412","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788374150.pdf","grobid_xml":"https://content.openalex.org/works/W2788374150.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1600744878","https://openalex.org/W1995562189","https://openalex.org/W1997449813","https://openalex.org/W2064675550","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2117671523","https://openalex.org/W2129334286","https://openalex.org/W2145247325","https://openalex.org/W2155273149","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2288402171","https://openalex.org/W2291522532","https://openalex.org/W2293634267","https://openalex.org/W2396144419","https://openalex.org/W2400505028","https://openalex.org/W2402146185","https://openalex.org/W2475988411","https://openalex.org/W2510349098","https://openalex.org/W2594610113","https://openalex.org/W2622203030","https://openalex.org/W2729190387","https://openalex.org/W2747006787","https://openalex.org/W2935927048","https://openalex.org/W2949192817","https://openalex.org/W2962835968","https://openalex.org/W2962965465","https://openalex.org/W6635768407","https://openalex.org/W6637373629","https://openalex.org/W6638205174","https://openalex.org/W6638444622","https://openalex.org/W6638545294","https://openalex.org/W6676716484","https://openalex.org/W6679446661","https://openalex.org/W6684191040","https://openalex.org/W6687483927","https://openalex.org/W6687812937","https://openalex.org/W6696224498","https://openalex.org/W6696934422","https://openalex.org/W6696972928","https://openalex.org/W6712557042","https://openalex.org/W6712772800","https://openalex.org/W6712930963","https://openalex.org/W6713606482","https://openalex.org/W6733140621","https://openalex.org/W6738686518","https://openalex.org/W6740627434"],"related_works":["https://openalex.org/W2963654251","https://openalex.org/W3126364007","https://openalex.org/W3200690474","https://openalex.org/W2767317683","https://openalex.org/W2949407480","https://openalex.org/W2949192817","https://openalex.org/W3102785448","https://openalex.org/W2991955089","https://openalex.org/W3127824595","https://openalex.org/W2293634267","https://openalex.org/W3096509852","https://openalex.org/W3083164447","https://openalex.org/W2897725921","https://openalex.org/W2620837403","https://openalex.org/W3021469861","https://openalex.org/W2977623724","https://openalex.org/W3188973088","https://openalex.org/W3015199127","https://openalex.org/W3009445297","https://openalex.org/W2804644188"],"abstract_inverted_index":{"Time":[0],"delay":[1],"neural":[2,108],"networks":[3],"(TDNNs)":[4],"are":[5,36,133],"an":[6],"effective":[7],"acoustic":[8],"model":[9,19,28],"for":[10,129],"large":[11],"vocabulary":[12],"speech":[13],"recognition.":[14],"The":[15,64,91,118],"strength":[16],"of":[17,49,69,82,88,93,105,127,181],"the":[18,41,51,56,60,80,83,86,89,97,100,103,147,160,172],"can":[20,136],"be":[21,137],"attributed":[22],"to":[23,26,85,99],"its":[24],"ability":[25],"effectively":[27],"long":[29],"temporal":[30,62],"contexts.":[31],"However,":[32],"current":[33],"TDNN":[34,61,101],"models":[35],"relatively":[37],"shallow,":[38],"which":[39],"limits":[40],"modelling":[42],"capability.":[43],"This":[44],"paper":[45],"proposes":[46],"a":[47,75,106,112,122,142,177],"method":[48],"increasing":[50],"network":[52,109],"depth":[53],"by":[54,140,165],"deepening":[55],"kernel":[57,67,157],"used":[58,134],"in":[59,102],"convolutions.":[63],"best":[65],"performing":[66],"consists":[68],"three":[70],"fully":[71],"connected":[72],"layers":[73],"with":[74,171],"residual":[76],"(ResNet)":[77],"connection":[78],"from":[79],"output":[81,87],"first":[84],"third.":[90],"addition":[92],"spectro-temporal":[94],"processing":[95],"as":[96],"input":[98],"form":[104],"convolutional":[107],"(CNN)":[110],"and":[111,135,168],"newly":[113],"designed":[114],"Grid-RNN":[115,119,175],"was":[116],"investigated.":[117],"strongly":[120],"outperforms":[121],"CNN":[123],"if":[124],"different":[125,130],"sets":[126],"parameters":[128],"frequency":[131,173],"bands":[132],"further":[138],"enhanced":[139],"using":[141,146],"bi-directional":[143],"Grid-RNN.":[144],"Experiments":[145],"multi-genre":[148],"broadcast":[149],"(MGB3)":[150],"English":[151],"data":[152],"(275h)":[153],"show":[154],"that":[155],"deep":[156],"TDNNs":[158],"reduces":[159],"word":[161],"error":[162],"rate":[163],"(WER)":[164],"6%":[166],"relative":[167,178],"when":[169],"combined":[170],"dependent":[174],"gives":[176],"WER":[179],"reduction":[180],"9%.":[182]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}